Below you will find pages that utilize the taxonomy term “M365 Copilot Extensibility”
posts
Generate OpenAPI Spec for M365 Copilot Declarative Agent
Introduction After encountering issues with creating a To-Do task action in my previous attempt Building a Copilot Agent with Microsoft 365 Agents Toolkit and Microsoft Graph Plugin to list my ToDo Tasks, I explored various methods to generate an OpenAPI specification for M365 Copilot Declarative Agents using the Ms Graph OpenAPI spec. This post outlines the different approaches I tried, the challenges I faced, and the lessons learned.
Methods for Generating OpenAPI Specs 1.
posts
Limitations of OpenAPI Spec with Complex Objects in Copilot Declarative Agents
Introduction In a previous post, I detailed the steps for Building a Copilot Agent with Microsoft 365 Agents Toolkit and Microsoft Graph Plugin to list my ToDo Tasks. However, I encountered issues with the CreateTask function when using an OpenAPI spec generated with Kiota. Upon investigation, I identified the problem as being related to the handling of complex objects, particularly those involving dates. Even after simplifying the object structure, the CreateTask function continued to fail.
posts
Microsoft Graph: Challenges with UserInformationList Search and Filter
Introduction When working with the UserInformationList in SharePoint via Microsoft Graph, you might encounter challenges when trying to search or filter user information. This post highlights the issues I faced while attempting to use $search and $filter queries on the UserInformationList, along with examples and insights within M365 Copilot declarative agent.
Issue 1: Search by Email Did Not Work I attempted to search for a user by their email address using the $search query, but it did not return any results.
posts
Step by step guide to integrate Microsoft 365 Copilot declarative agents with Azure AI Search
Introduction In this post, I’ll walk you through how to call Azure AI Search APIs from a M365 Copilot declarative agent without writing any code by using Microsoft 365 Agents Toolkit. Leveraging OpenAPI specifications, Microsoft 365 Agents Toolkit (previously known as Teams Toolkit) enables seamless integration with Azure AI Search, streamlining the development process for Copilot extensibility.
Waldek Mastykarz wrote an insightful post on when Azure AI Search can be used, highlighting its ability to provide a more controlled approach to indexing and relevance without the complexity of building a custom engine agent.
posts
Step by step guide to integrate Microsoft 365 Copilot declarative agents with Azure OpenAI
Introduction In this post, I’ll walk you through how to call Azure OpenAI APIs from a Copilot declarative agent—without writing any code—by using Microsoft 365 Agents Toolkit. Leveraging OpenAPI specifications, Microsoft 365 Agents Toolkit enables seamless integration with Azure OpenAI, streamlining the development process for Copilot extensibility.
Step 1: Create and Import an OpenAPI Specification Microsoft provides a pre-built OpenAPI specification for Azure OpenAI, but it’s often broader than needed. To simplify, I generated a targeted OpenAPI spec with Copilot by using the endpoint URL and a sample request body as a prompt.
posts
Building a Copilot Agent with Microsoft 365 Agents Toolkit and Microsoft Graph Plugin to list my ToDo Tasks
Introduction This guide walks you through creating a Copilot agent using Microsoft 365 Agents Toolkit (previously known as Teams Toolkit) and Microsoft Graph API. By leveraging OpenAPI specifications, Kiota, and Microsoft 365 Agents Toolkit, you can build a plugin to interact with Microsoft Graph endpoints. I used the blog post Copilot Graph API QnA Plugin by Franck Cornu as inspiration with some variation to apply it to get my ToDo tasks.
posts
Troubleshooting Microsoft Graph Plugin Issues in Copilot Agents Built with Microsoft 365 Agents Toolkit
Introduction When building a Copilot agent using Microsoft 365 Agents Toolkit (previously known as Teams Toolkit), you may encounter certain errors that can hinder your progress. This blog post highlights common issues and provides solutions to help you resolve them effectively.
Common Issues and Fixes 1. name_for_human Exceeds 20 Characters Issue: You may encounter the following error when the name_for_human field in the ai-plugin.json file exceeds 20 characters:
name_for_human in PluginManifestDocument has characters beyond the length 20 that MAY be ignored.